arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.12553math.OC
收藏

用对数-对数凸规划进行微分

Differentiating through Log-Log Convex Programs

Akshay Agrawal, Stephen Boyd

摘要:

我们展示了如何有效地计算导数(当它存在时)的对数对数凸规划(LLCP)的解决方案映射。这些是非凸的、非光滑最优化问题,当变量、目标函数和约束函数被替换为它们的日志时,正变量就会变成凸的。我们专注于LLCP产生的纪律几何规划,一个语法组成的一组原子功能与已知的对数-对数曲率和组合它们的规则。我们将参数化LLCP表示为参数的平滑变换、凸优化问题和凸优化问题解的指数变换的组合。该组合的导数可以有效地计算,使用最近开发的方法区分通过凸优化问题。我们实现了我们的方法在CVXPY,Python嵌入式建模语言和重写系统的凸优化。在短短几行代码中,用户可以指定参数化LLCP,求解它,并计算导数或其伴随向量。这使得有可能进行灵敏度分析的解决方案,给定扰动的参数,并计算梯度的函数的解决方案相对于参数。我们使用导数的伴随来实现PyTorch和TensorFlow中的可微对数-对数凸优化层。最后,我们提出的应用程序设计排队系统和拟合结构化预测模型。

英文摘要:

We show how to efficiently compute the derivative (when it exists) of the solution map of log-log convex programs (LLCPs). These are nonconvex, nonsmooth optimization problems with positive variables that become convex when the variables, objective functions, and constraint functions are replaced with their logs. We focus specifically on LLCPs generated by disciplined geometric programming, a grammar consisting of a set of atomic functions with known log-log curvature and a composition rule for combining them. We represent a parametrized LLCP as the composition of a smooth transformation of parameters, a convex optimization problem, and an exponential transformation of the convex optimization problem's solution. The derivative of this composition can be computed efficiently, using recently developed methods for differentiating through convex optimization problems. We implement our method in CVXPY, a Python-embedded modeling language and rewriting system for convex optimization. In just a few lines of code, a user can specify a parametrized LLCP, solve it, and evaluate the derivative or its adjoint at a vector. This makes it possible to conduct sensitivity analyses of solutions, given perturbations to the parameters, and to compute the gradient of a function of the solution with respect to the parameters. We use the adjoint of the derivative to implement differentiable log-log convex optimization layers in PyTorch and TensorFlow. Finally, we present applications to designing queuing systems and fitting structured prediction models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑